欢迎访问《图学学报》 分享到：
图学学报

图学学报 ›› 2021, Vol. 42 ›› Issue (1): 52-58.DOI: 10.11996/JG.j.2095-302X.2021010052

• 图像处理与计算机视觉 • 上一篇    下一篇

一种水下鱼类动态视觉序列运动目标检测方法

  

  1. 1. 上海海洋大学信息学院，上海 201306； 2. 上海电力大学，上海 200090
  • 出版日期:2021-02-28 发布日期:2021-02-01
  • 基金资助:
    国家自然科学基金面上项目(61972240)；上海市科委能力建设项目(17050501900)，大洋渔业资源可持续开发教育部重点实验室开放基 金项目(A1-2006-00-301104) 

Method for moving object detection of underwater fish using dynamic video sequence 

  1. 1. College of Information Technology, Shanghai Ocean University, Shanghai 201306, China;  2. Shanghai University of Electric Power, Shanghai 200090, China
  • Online:2021-02-28 Published:2021-02-01
  • Supported by:
    General Program of National Natural Science Foundation of China (61972240); Science and Technology Commission of Shanghai Capacity Building Projects (17050501900); Open Fund Project of Key Laboratory of Ministry of Eeducation for Sustainable Development of Ocean Fishery Resources (A1-2006-00-301104) 

PDF (PC)

101

摘要： 针对水下视频质量不高、视频模糊不清甚至很难辨认的问题，利用计算机视觉技术对水下鱼类 目标进行快速目标检测，提出了一种基于背景去除的水下视频目标检测方法。设计适合水下环境的鱼类目标检 测框架，使用偏最小二乘(PLS)分类器进行目标检测。利用水下拍摄的鱼类数据集收集输入的视频序列，并提 取单独的帧。将帧的 RGB 格式转换为 HSI 格式并进行中值滤波器去噪的预处理，利用 GMG 背景去除过程， 提取了基于局部二值模式(LBP)纹理和灰度系数的重要特征，最后将所提取的特征，利用 PLS 分类器，实现了 分别对白天及夜晚环境中的水下鱼类目标检测。结果表明，该方法在水下拍摄的鱼类视频数据集目标检测精度 可达 96.89%，提高了检测效率，降低了人工成本。为水下鱼类等生物资源的监测、保护和可持续开发等工程 应用提供了一定的参考价值。

关键词: 偏最小二乘, 背景去除, 鱼类, 目标检测, 动态视觉序列

Abstract: In order to overcome the problems of underwater videos, such as low quality, blurring and even unrecognizability, using the computer vision technology for fast detection of underwater fish targets, an underwater video object detection method was proposed based on background removal methods. An object detection framework for underwater fish was designed, using the partial least squares (PLS) classifier for object detection. Input video sequences were collected from underwater fish data sets, and individual frames were extracted. After the format conversion of RGB to HSI and median filter denoising pretreatment, using the GMG background removal process, the texture and the characteristic of the gray scale coefficient were extracted based on local binary (LBP) pattern. At last, with the above extracted characteristics, the object detection of underwater fish in the daytime and night was realized using the PLS classifier. The results show that the method can achieve the object detection accuracy of 96.89% using the underwater fish video datasets, which improves the detection efficiency of underwater fish and reduces the labor cost. It can also provide some guidance for the monitoring, protection and sustainable development of underwater fish and other biological resources. 

Key words:  , partial least squares, background removal, fish, object detection, dynamic video sequence 

中图分类号: